{"id":"https://openalex.org/W7127993432","doi":"https://doi.org/10.48550/arxiv.2602.05639","title":"Joint Embedding Variational Bayes","display_name":"Joint Embedding Variational Bayes","publication_year":2026,"publication_date":"2026-02-05","ids":{"openalex":"https://openalex.org/W7127993432","doi":"https://doi.org/10.48550/arxiv.2602.05639"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.05639","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125176810","display_name":"Amin Oji","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Oji, Amin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125210033","display_name":"Paul Fieguth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fieguth, Paul","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5125176810"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.45100000500679016,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.45100000500679016,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.17659999430179596,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11420000344514847,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6403999924659729},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5619999766349792},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5425000190734863},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.450300008058548},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.42669999599456787},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41920000314712524},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4172999858856201},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.4092000126838684},{"id":"https://openalex.org/keywords/marginal-likelihood","display_name":"Marginal likelihood","score":0.3968999981880188},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.3815000057220459}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6403999924659729},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48919999599456787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46560001373291016},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.450300008058548},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.42669999599456787},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C95923904","wikidata":"https://www.wikidata.org/wiki/Q6760420","display_name":"Marginal likelihood","level":3,"score":0.3968999981880188},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.37470000982284546},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.35659998655319214},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.35249999165534973},{"id":"https://openalex.org/C162929932","wikidata":"https://www.wikidata.org/wiki/Q129638","display_name":"Grassmannian","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C55974624","wikidata":"https://www.wikidata.org/wiki/Q1188504","display_name":"Exponential family","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3041999936103821},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C50820777","wikidata":"https://www.wikidata.org/wiki/Q213723","display_name":"Hypercube","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C122268817","wikidata":"https://www.wikidata.org/wiki/Q2020318","display_name":"Frank\u2013Wolfe algorithm","level":5,"score":0.2849000096321106},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C111110010","wikidata":"https://www.wikidata.org/wiki/Q2627315","display_name":"Convex combination","level":4,"score":0.2815000116825104},{"id":"https://openalex.org/C158968445","wikidata":"https://www.wikidata.org/wiki/Q7631150","display_name":"Subgradient method","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.26649999618530273}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.05639","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.05639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.05639","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.05639","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,150],"introduce":[1],"Variational":[2],"Joint":[3],"Embedding":[4],"(VJE),":[5],"a":[6,19,32,42,51,56,64,86,101,170],"reconstruction-free":[7],"latent-variable":[8],"framework":[9,168],"for":[10,90,146],"non-contrastive":[11,131,175],"self-supervised":[12],"learning":[13],"in":[14,143,177,185],"representation":[15,58,144],"space.":[16,189],"VJE":[17,126],"maximizes":[18],"symmetric":[20],"conditional":[21,33],"evidence":[22],"lower":[23],"bound":[24,89],"(ELBO)":[25],"on":[26,36,55,81],"paired":[27],"encoder":[28],"embeddings":[29],"by":[30],"defining":[31],"likelihood":[34,47],"directly":[35,142,184],"target":[37,61],"representations,":[38],"rather":[39],"than":[40],"optimizing":[41],"pointwise":[43],"compatibility":[44],"objective.":[45],"The":[46,77],"is":[48,127,182],"instantiated":[49],"as":[50,169],"heavy-tailed":[52],"Student--\\(t\\)":[53],"distribution":[54],"polar":[57],"of":[59,174],"the":[60,82,91,111,167,186],"embedding,":[62],"where":[63,157],"directional--radial":[65],"decomposition":[66],"separates":[67],"angular":[68],"agreement":[69],"from":[70],"magnitude":[71],"consistency":[72],"and":[73,124,135],"mitigates":[74],"norm-induced":[75],"pathologies.":[76],"directional":[78,112],"factor":[79],"operates":[80],"unit":[83],"sphere,":[84],"yielding":[85,114],"valid":[87],"variational":[88,172],"associated":[92],"spherical":[93],"subdensity":[94],"model.":[95],"An":[96],"amortized":[97],"inference":[98],"network":[99],"parameterizes":[100],"diagonal":[102],"Gaussian":[103],"posterior":[104],"whose":[105],"feature-wise":[106,180],"variances":[107],"are":[108],"shared":[109],"with":[110,129],"likelihood,":[113],"anisotropic":[115],"uncertainty":[116,181],"without":[117],"auxiliary":[118],"projection":[119],"heads.":[120],"Across":[121],"ImageNet-1K,":[122],"CIFAR-10/100,":[123],"STL-10,":[125],"competitive":[128],"standard":[130],"baselines":[132],"under":[133],"linear":[134],"\\(k\\)-NN":[136],"evaluation,":[137],"while":[138],"providing":[139],"probabilistic":[140],"semantics":[141,153],"space":[145],"downstream":[147],"uncertainty-aware":[148],"applications.":[149],"validate":[151],"these":[152],"through":[154],"out-of-distribution":[155],"detection,":[156],"representation-space":[158],"likelihoods":[159],"yield":[160],"strong":[161],"empirical":[162],"performance.":[163],"These":[164],"results":[165],"position":[166],"principled":[171],"formulation":[173],"learning,":[176],"which":[178],"structured":[179],"represented":[183],"learned":[187],"embedding":[188]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-07T00:00:00"}